Research

Jump directly to:

  1. Projects
  2. Publications
  3. Theses
  4. Talks
  5. Software
  6. Biography

Projects

Current projects

  • MODIR - Multi-objective deformable image registration for medical images, using evolutionary algorithms
    • Period: November 2020 - present
    • Research conducted as PhD candidate at the Radiation Oncology department at the LUMC (Leiden, NL) and the Life Sciences & Health group at the CWI (Amsterdam, NL). Supervised by dr. Tanja Alderliesten (LUMC) and prof.dr. Peter A.N. Bosman (CWI, TUD).

Previous projects

  • Capelin - Fast Data-Driven Capacity Planning for Cloud Datacenters
  • OpenDC - Collaborative Datacenter Simulation and Exploration for Everybody
    • Period: May 2016 - August 2020
    • Research conducted during B.Sc. Honours project and M.Sc. thesis project.
    • Supervised by prof.dr. Alexandru Iosup.
  • SCHAAPI - Early Detection of Breaking Changes Based on API Usages
    • Period: April 2018 - July 2018
    • Research conducted during B.Sc. thesis project.
    • Supervised by dr. Mauricio Aniche.

Publications

Listed in reverse chronological order

  1. Andreadis, G., Mulder, J.I., Bouter, A., Bosman, P.A.N., & Alderliesten, T. (2024, February). A tournament of transformation models: B-Spline-based vs. mesh-based multi-objective deformable image registration. In SPIE Medical Imaging 2022: Image Processing (Vol. 12926). SPIE. [arXiv]
  2. Andreadis, G., Bosman, P.A.N., & Alderliesten, T. (2023, July). MOREA: a GPU-accelerated Evolutionary Algorithm for Multi-Objective Deformable Registration of 3D Medical Images. In Proceedings of the 2023 Genetic and Evolutionary Computation Conference (pp. 1294–1302). ACM. [ACM] [arXiv]
  3. Andreadis, G., Bosman, P.A.N., & Alderliesten, T. (2022, April). Multi-objective dual simplex-mesh based deformable image registration for 3D medical images - proof of concept. In SPIE Medical Imaging 2022: Image Processing (Vol. 12032, pp. 744-750). SPIE. [SPIE] [arXiv]
  4. Andreadis, G., Mastenbroek, F., Van Beek, V., & Iosup, A. (2021, May). Capelin: Data-Driven Compute Capacity Procurement for Cloud Datacenters using Portfolios of Scenarios. In Transactions on Parallel and Distributed Systems. IEEE. [IEEE] [ResearchGate Technical Report] [ResearchGate Main Article]
  5. Mastenbroek, F., Andreadis, G., Jounaid, S., Lai, W., Burley, J., Bosch, J., van Eyk, E., Versluis, L., van Beek, V., & Iosup, A. (2021, May). OpenDC 2.0: Convenient modeling and simulation of emerging technologies in cloud datacenters. In 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid) (pp. 455-464). IEEE. [IEEE]
  6. Andreadis, G., Versluis, L., Mastenbroek, F., & Iosup, A. (2018, November). A reference architecture for datacenter scheduling: design, validation, and experiments. In SC18: International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 478-492). IEEE. [ACM] [ResearchGate]
  7. Iosup, A., Uta, A., Versluis, L., Andreadis, G., Van Eyk, E., Hegeman, T., Talluri, S., van Beek, V., & Toader, L. (2018, July). Massivizing computer systems: a vision to understand, design, and engineer computer ecosystems through and beyond modern distributed systems. In ICDS: International Conference on Distributed Computing Systems (pp. 1224-1237). IEEE. [IEEE] [ResearchGate]
  8. Iosup, A., Andreadis, G., Van Beek, V., Bijman, M., Van Eyk, E., Neacsu, M., Overweel, L., Talluri, S., Versluis, L. & Visser, M. (2017, July). The OpenDC vision: Towards collaborative datacenter simulation and exploration for everybody. In ISPDC: International Symposium on Parallel and Distributed Computing (pp. 85-94). IEEE. [IEEE] [ResearchGate]

Theses

Listed in reverse chronological order

  1. M.Sc. thesis: Andreadis, G. (2020, August). Capelin: Fast Data-Driven Capacity Planning for Cloud Datacenters. TU Delft. [Thesis] (Awarded Best Graduate of TU Delft 2020)
  2. B.Sc. thesis: Abrahams, J., Andreadis, G., Boone, C., & Dekker, F. (2018, July). Schaapi: Early detection of breaking changes based on API usage. [Thesis]

Talks

Listed in reverse chronological order

  • 24 May 2023: Research pitch on my PhD project at the LUMC Cancer Research Day. [received Best Pitch award]
  • 18 May 2022: Highlight talk on my PhD research, for users and staff of the HPC clusters of the medical center and university. ALICE-SHARK User Meeting, Leiden University.
  • 14 December 2021: Lunch lecture for students of the EEMCS faculty on my past and current research. Organized by Study Association Christiaan Huygens, Delft University of Technology. [invited talk]
  • 14 November 2018: Paper presentation on my paper on a reference architecture for schedulers at Supercomputing 2018, Dallas TX.

Software

Current software projects

  • Statistak - Tour Log and Statistics for the Ricciotti Ensemble [Website]
    • Role: Designer and developer

Previous software projects

  • We\Visit - Platform for relatives to connect with patients in hospital through video calls [Website]
    • Role: Volunteer Maintainer & Developer
  • OpenDC - Online datacenter simulator with emphasis on visualization and education [Website]
    • Role: Frontend engineer, later technology lead
  • qEHBO - Dutch First Aid Mobile Training App [GitHub]
    • Role: Initiator, designer, and developer
  • Support NJON - Site to support the National Youth Orchestra of the Netherlands funding campaign [Website]
    • Role: Web designer and developer

Biography

Ir. Georgios Andreadis is a PhD candidate at the Leiden University Medical Center (LUMC) and guest researcher in the Life Sciences and Health (LSH) research group at the Centrum Wiskunde & Informatica (CWI), under supervision of dr. Tanja Alderliesten and prof.dr. Peter A.N. Bosman. Andreadis obtained his BSc and MSc degrees in Computer Science at Delft University of Technology in 2020. For his MSc thesis research on cloud capacity planning, he was awarded the title of Best Graduate of the TU Delft. The focus of his current PhD research is on multi-objective deformable image registration for medical images, using evolutionary algorithms. The large anatomical differences frequently present between medical scans of patients make transferring knowledge between scans an open challenge. In his research, he aims to find a method for deformable image registration that is flexible and reliable enough for clinical application but also involves the expertise of clinical users into the process.